orchestrator

Enforce centralized decision gating and context loading across agent turns.

Updated Aug 23, 2026
One-click install
npx skills add https://github.com/dylan-conlin/orch-go --skill orchestrator-dylan-conlin
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: orchestrator
Source: https://github.com/dylan-conlin/orch-go/tree/main/skills/src/meta/orchestrator
Command: npx skills add https://github.com/dylan-conlin/orch-go --skill orchestrator-dylan-conlin

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill provides an always-loaded runtime policy that governs orchestrator agents, ensuring consistent behavior across turns, loading reference documents on demand, and preserving a coherent frame for agent actions.

Core Features & Use Cases

  • Roles: COMPREHEND, TRIAGE, SYNTHESIZE, with clear responsibilities and interaction flow.
  • Context Detection & Fast Path: standardized decision gates to route work, avoid unsafe spawns, and surface comprehension.
  • Reference docs and governance: loads operational guidance and ensures narrativized synthesis later.

Quick Start

Load the orchestrator policy into your runtime so it is active for every turn.

Frequently Asked Questions about orchestrator

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I ensure consistent agent workflow governance across multiple turns?

Agent workflow governance requires an always-on runtime policy that centralizes decision gating and context loading. This ensures consistent behavior across turns by enforcing phase verification and standardized interaction flows for all agent roles.

What is centralized orchestrator policy and how does it guide agent behavior?

Centralized orchestrator policy is an always-loaded runtime framework that guides agent actions by enforcing context loading, phase verification, and governance over spawning. It applies unified decision gates across comprehension, triage, and synthesis roles.

How do I prevent unsafe agent spawning during complex task synthesis?

Preventing unsafe agent spawning requires standardized decision gates that route work based on context detection. The orchestrator policy uses fast path routing and phase verification to evaluate safety before allowing agents to spawn new processes.

Do I need to manually load reference documents for agent context detection?

Manual reference document loading is unnecessary because the orchestrator policy automatically loads operational guidance on demand. It handles context detection dynamically during each turn, ensuring agents have required reference materials without manual intervention.

Can I use orchestrator policy for triage and comprehension roles simultaneously?

Orchestrator policy supports triage and comprehension roles simultaneously by applying centralized governance across all agent roles. It defines clear responsibilities and interaction flows for COMPREHEND, TRIAGE, and SYNTHESIZE phases within a single coherent runtime frame.

Why does my agent lose context coherence between separate workflow sessions?

Agent context coherence between sessions is lost without an always-loaded runtime policy enforcing consistent behavior. The orchestrator policy preserves a coherent frame for agent actions by centralizing guidance and applying phase verification across all session turns.